© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12638
    Prev
    Next
    INDEX
    Explanations

    words related to governmental administrative, financial and legal topics with a spattering of violence and personal change

    oai_token-act-pair · gemini-2.0-flash

    various topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afficheront
    -0.61
    CppCodeGen
    -0.60
     snippetHide
    -0.60
    UnusedPrivate
    -0.59
    原始内容存档于
    -0.56
     Sunni
    -0.56
    <bos>
    -0.55
     joaat
    -0.55
    migrationBuilder
    -0.54
    libft
    -0.54
    POSITIVE LOGITS
     chaînes
    0.46
     letz
    0.45
    ucoup
    0.45
    iffion
    0.44
     trưởng
    0.43
    مقاله
    0.42
    uate
    0.42
     aigu
    0.41
     käns
    0.41
     répondit
    0.41
    Activations Density 0.857%

    No Known Activations